Senior Data Scientist
About The Position
As a Senior Data Scientist at Samsung Austin Semiconductor, you will build and deploy machine learning systems that improve semiconductor manufacturing processes, focusing on anomaly detection, root cause analysis, and virtual metrology. The work primarily involves high-frequency time-series and tabular data, including feature engineering, model training, and communicating clear, actionable results to process engineers. You will own the full model lifecycle, from data preparation and algorithm selection through deployment, monitoring, and ongoing tuning. The team works collaboratively in a sprint-driven environment. You will have autonomy to design technical approaches, test methods, and iterate based on feedback. Prior semiconductor experience is helpful but not required; domain knowledge is developed through hands-on projects and team support.
Requirements
- Bachelor’s degree or higher in Data Science, Statistics, Computer Science, Physics, or a related quantitative field.
- At least 5 years of professional experience designing, training, and deploying machine learning models.
- Working knowledge of regression, classification, ensemble methods, feature engineering, and model evaluation metrics.
- Advanced proficiency in Python for data analysis and modeling.
- Strong SQL skills for extracting and transforming large datasets.
- Experience building and maintaining machine learning pipelines for experiment tracking, model versioning, automated retraining, and live performance monitoring.
Nice To Haves
- Master’s or PhD degree.
- Prior semiconductor experience.
- Track record of turning open-ended questions into clear machine learning problems and delivering models that run reliably in production.
- Hands-on experience with tabular data techniques such as categorical encoding, missing-value imputation, and model interpretability methods such as SHAP.
- Comfort working in an Agile environment, prototyping quickly, validating results with real data, and refining models based on direct feedback from engineering teams.
- Practical experience using PySpark to process, transform, and scale large datasets for machine learning workflows.
Responsibilities
- Build supervised machine learning models for anomaly detection using high-frequency tabular and time-series data.
- Enhance data collection and processing workflows to create robust, high-quality test datasets that support model accuracy, relevance, and integrity.
- Design, train, and iterate on predictive models integrating process and quality data, including algorithm selection, feature engineering, and rigorous model validation.
- Engineer features from continuous time-series streams, combine process variables, and develop methods for handling missing or sparse data.
- Manage modeling workflows, including cross-validation, hyperparameter tuning, experiment tracking, model versioning, and automated retraining schedules.
- Set statistical benchmarks for model performance and monitor deployed models in production.
- Communicate technical findings to data scientists and process engineers.
Benefits
- Medical insurance
- Dental insurance
- Vision insurance
- Life insurance
- 401(k) matching with immediate vesting
- Onsite cafés and workout facilities
- Paid maternity leave
- Paid paternity leave
- Paid time off (PTO)
- Two personal holidays and 10 regular holidays
- Wellness incentives
- Eligible full-time employees may receive MBO bonuses based on company, division, and individual performance
- Competitive benefits package
- May include participation in company incentive compensation programs
Stand Out From the Crowd
Upload your resume and get instant feedback on how well it matches this job.
What This Job Offers
Job Type
Full-time
Career Level
Senior
